© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97338
    Prev
    Next
    INDEX
    Explanations

    views/scenery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.59
    RenderAtEndOf
    -0.57
    ötz
    -0.55
    odils
    -0.53
     intent
    -0.52
    útbol
    -0.52
    Vidite
    -0.51
     devotion
    -0.51
    átní
    -0.51
     allure
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.71
     &___
    0.69
     and
    0.59
     of
    0.56
    gameserver
    0.56
    ynb
    0.56
    UseVisualStyle
    0.55
     surla
    0.55
    WriteLiteral
    0.53
    MemoryWarning
    0.53
    Activations Density 0.005%

    No Known Activations